LE

LexiLumin 34B i1

LexiluminGGUF by mradermacherUpdated 2024-05-05
Download on Hugging Face
Parameters33.4B
Context32K
Layers152
Architecturellama
Smallest quant7.2 GB
Quick answer

LexiLumin 34B i1 needs about 25.7 GB of memory at Q4_K_M (a 20.1 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 21 quants, from 7.2 GB (IQ1_S) to 27.4 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 20.4 GB.

LexiLumin 34B i1 is a 33.4B-parameter Lexilumin model in GGUF format, quantized by mradermacher. Its trained context length is 32K tokens. The repository has 21 quant files, from 7.2 GB (IQ1_S) to 27.4 GB (Q6_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S7.2 GB 12.8 GB
Too big Get file →
IQ1_M7.8 GB 13.4 GB
Too big Get file →
IQ2_XXS9.0 GB 14.6 GB
Too big Get file →
IQ2_XS9.9 GB 15.5 GB
Too big Get file →
IQ2_S10.4 GB 16.0 GB
Too big Get file →
IQ2_M11.3 GB 16.9 GB
Too big Get file →
Q2_K12.3 GB 17.9 GB
Too big Get file →
IQ3_XXS12.9 GB 18.5 GB
Too big Get file →
IQ3_XS13.7 GB 19.3 GB
Too big Get file →
Q3_K_S14.4 GB 20.0 GB
Too big Get file →
IQ3_S14.5 GB 20.1 GB
Too big Get file →
IQ3_M15.0 GB 20.6 GB
Too big Get file →
Q3_K_M16.1 GB 21.7 GB
Too big Get file →
Q3_K_L17.5 GB 23.1 GB
Too big Get file →
IQ4_XS17.9 GB 23.5 GB
Too big Get file →
Q4_018.9 GB 24.5 GB
Too big Get file →
Q4_K_S19.0 GB 24.6 GB
Too big Get file →
Q4_K_M20.1 GB 25.7 GB
Too big Get file →
Q5_K_S23.0 GB 28.6 GB
Too big Get file →
Q5_K_M23.6 GB 29.2 GB
Too big Get file →
Q6_K27.4 GB 33.0 GB
Too big Get file →

What GPU do you need for LexiLumin 34B i1?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: no quant fits at an 8K context.
  • 6 GB VRAM: no quant fits at an 8K context.
  • 8 GB VRAM: no quant fits at an 8K context.
  • 12 GB VRAM: no quant fits at an 8K context.
  • 16 GB VRAM: the best quant that fits is IQ2_S (10.4 GB file, about 16.0 GB in use).
  • 24 GB VRAM: the best quant that fits is IQ4_XS (17.9 GB file, about 23.5 GB in use).
  • 32 GB VRAM: the best quant that fits is Q5_K_M (23.6 GB file, about 29.2 GB in use).
  • 48 GB VRAM: the best quant that fits is Q6_K (27.4 GB file, about 33.0 GB in use).

Which LexiLumin 34B i1 quant should you choose?

Q4_K_M is the usual starting point for LexiLumin 34B i1: it balances file size and quality well. Here it is a 20.1 GB file.

If memory is tight, the smallest file is IQ1_S at 7.2 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters33.4B
Layers152
Trained context32,768 tokens
KV cache (fp16)608 KB per token

Source

Quantized bymradermacher
FamilyLexilumin
Downloads (HF)99
Last updated2024-05-05

Frequently asked questions about LexiLumin 34B i1

How much VRAM does LexiLumin 34B i1 need?

About 25.7 GB at Q4_K_M with an 8K context window. That is the 20.1 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run LexiLumin 34B i1 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 12.8 GB, so you would need a larger GPU or CPU offloading.

What is the file size of LexiLumin 34B i1 GGUF?

It depends on the quant: IQ1_S is 7.2 GB, IQ1_M is 7.8 GB, IQ2_XXS is 9.0 GB, IQ2_XS is 9.9 GB, IQ2_S is 10.4 GB, IQ2_M is 11.3 GB and 15 more.

What context length does LexiLumin 34B i1 support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 5.1 GB at 8K and 20.4 GB at 32K.

Where can I download LexiLumin 34B i1 GGUF?

The files are on Hugging Face in the mradermacher/LexiLumin-34B-i1-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Lexilumin models

All Lexilumin →

Other medium models

All medium models →